xAI

grok-4.3

Made by xAI. Released 2026-04-17. Accessibility not recorded. Cheapest standard rate we hold: $2.50 per million output tokens, at < 200k prompt tokens context.

What it costs

TierKindInOutCached inFrom
standardtext · < 200k prompt tokens$1.25$2.50$0.20seller
standardtext · ≥ 200k prompt tokens$2.50$5$0.40seller

per million tokens, US dollars. * marks a rate from a single registry or two that disagree — the best available number rather than a confirmed one. Every other row is confirmed against a seller or a licensed index.

What it scores, by house

BenchmarkHouseScoreEvaluatedScaffold
chess puzzlesEpoch AI0.3±0.042026-06-17high
frontiermath tier 4 v2Epoch AI0.1±0.062026-06-17high
frontiermath tiers 1 3 v2Epoch AI0.4±0.032026-06-17high
gpqa diamondEpoch AI0.9±0.022026-06-17high
otis mock aime 2024 2025near its ceilingEpoch AI0.9±0.032026-06-17high
simpleqa verifiedEpoch AI0.3±0.012026-08-27high
ale benchcollected by Epoch AI944unknown
blueprint bench 2collected by Epoch AI0.0unknown
critptcollected by Epoch AI0.1high
critptcollected by Epoch AI0.0unknown
critptcollected by Epoch AI0.0none
dtbenchnear its ceilingcollected by Epoch AI0.9high
forecastbenchcollected by Epoch AI60.4unknown
gdp pdfcollected by Epoch AI0.1unknown
gdp pdfcollected by Epoch AI0.1high
lmcacollected by Epoch AI38.3high
proofbenchcollected by Epoch AI0.1high
scicodecollected by Epoch AI0.5high
vending bench 2collected by Epoch AI35.3unknown
webdev arenacollected by Epoch AI1357unknown
weirdmlcollected by Epoch AI0.5unknown

These scores are not comparable between houses and are not added up. A score is dated by when it was evaluated, not when the model was released, and a score without its scaffold is not a measurement — which is why both are printed.

Every rate we hold · Why there is no single best model · Everything from xAI